EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Vehicle Re-Identification Method Based on Efficient Self-Attention CNN-Transformer and Multi-Task Learning Optimization

Yu Wang iD, Rui Li, Yihan Shao

Sensors · 08.05.2025 · 25 (10) · 2977

DOI: 10.3390/s25102977 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 08.05.2025. Verfasst von Yu Wang und 2 weiteren Autor:innen. Beteiligte Einrichtung: College of Computer Science and Technology, Jilin University, Changchun 130012, China. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 26 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Jilin Province Science and Technology Department, Jilin Province Science and Technology Development Plan Key R&D Project.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

To address the challenges of low accuracy in vehicle re-identification caused by intra-class variations, inter-class similarities and environmental factors, this paper proposes a CNN-Transformer architecture (IBNT-Net) for vehicle re-identification. The method builds upon a ResNet50-IBN backbone network and incorporates an improved multi-head self-attention mechanism to aggregate contextual information. It constructs a multi-branch vehicle re-identification network that combines both global and local features. Furthermore, a multi-task learning strategy is adopted, creating specialized learning pathways for classification tasks and metric learning tasks. Group convolution techniques are utilized to reduce model complexity, making it suitable for resource-constrained environments. On the VeRi-776 and VehicleID dataset, the proposed method achieves state-of-the-art performance with less parameters. The experimental results show that the proposed method has better re-identification performance and the extracted features are more discriminative.

Schlagwörter

Stichwörter der Autor:innen

inter-class similaritiesintra-class variationsmulti-branch architecturemulti-task learningself-attention mechanismvehicle re-identification

Autor:innen und Institutionen

  • College of Computer Science and Technology, Jilin University, Changchun 130012, China.
  • College of Software, Jilin University, Changchun 130012, China.

ORCID-Profile: Yu Wang

Förderung

  • Jilin Province Science and Technology Department
  • Jilin Province Science and Technology Development Plan Key R&D Project

Zitieren

APA

Wang, Y., Li, R., & Shao, Y. (2025). Vehicle Re-Identification Method Based on Efficient Self-Attention CNN-Transformer and Multi-Task Learning Optimization. Sensors, 25(10), 2977. https://doi.org/10.3390/s25102977

Vancouver

Wang Y, Li R, Shao Y. Vehicle Re-Identification Method Based on Efficient Self-Attention CNN-Transformer and Multi-Task Learning Optimization. Sensors. 2025;25(10):2977. doi:10.3390/s25102977

BibTeX
@article{Wang2025,
  author = {Wang, Yu and Li, Rui and Shao, Yihan},
  title = {Vehicle Re-Identification Method Based on Efficient Self-Attention CNN-Transformer and Multi-Task Learning Optimization},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {10},
  pages = {2977},
  doi = {10.3390/s25102977}
}
Kostenlos starten →